{"id":"W107076218","doi":"10.1016/j.cag.2012.09.002","title":"High dynamic range image deghosting by fast approximate background modelling","year":2012,"lang":"en","type":"article","venue":"Computers & Graphics","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ghosting; Computer science; Computer vision; Artificial intelligence; High dynamic range; Segmentation; High-dynamic-range imaging; Frame (networking); A priori and a posteriori; Range (aeronautics); Frame rate; Dynamic range","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001241318,0.0003454197,0.0003731426,0.0002504765,0.0004062489,0.0005621986,0.00125156,0.0001376302,0.000003507603],"category_scores_gemma":[0.00001569773,0.0003599473,0.0001825995,0.0008355369,0.0001383173,0.001680554,0.000464788,0.0004253873,0.00003830787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006066782,"about_ca_system_score_gemma":0.00002969624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007588354,"about_ca_topic_score_gemma":9.198274e-7,"domain_scores_codex":[0.9973584,0.0002854716,0.000418891,0.0005601427,0.0004482512,0.0009288294],"domain_scores_gemma":[0.9982718,0.0003520302,0.0001946013,0.0007650499,0.0001393988,0.0002771854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001868352,0.001904833,0.002276248,0.0009414621,0.0006715377,0.0003381502,0.01353963,0.0224652,0.05064844,0.2943816,0.02319022,0.5894559],"study_design_scores_gemma":[0.0007122862,0.00004489404,0.0001737974,0.00006543653,0.0000239936,0.0000558602,0.00002330954,0.9924517,0.0009276315,0.004227294,0.0007840202,0.0005097256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03807015,0.001284936,0.9581473,0.0002138453,0.001539442,0.0001769533,0.000006618369,0.0003922033,0.000168533],"genre_scores_gemma":[0.2999619,0.00006890301,0.6990053,0.0006939053,0.0001552629,0.000008268412,0.00001741746,0.00003675714,0.00005224618],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9699866,"threshold_uncertainty_score":0.9998853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02912554906638193,"score_gpt":0.2686937490590583,"score_spread":0.2395681999926764,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}